Generate images from text and images using custom LoRA and Z-Image Turbo, Tongyi-MAI's super-fast 6B model.

fal-ai/z-image/turbo/image-to-image/lora

Generate images from text and images using custom LoRA and Z-Image Turbo, Tongyi-MAI's super-fast 6B model.

Learn more about Z-Image

Inference

Commercial use

Schema

LLMs

Playground API

Input

Prompt*

A young Asian woman with long, vibrant purple hair stands on a sunlit sandy beach, posing confidently with her left hand resting on her hip. She gazes directly at the camera with a neutral expression. A sleek black ribbon bow is tied neatly on the right side of her head, just above her ear. She wears a flowing white cotton dress with a fitted bodice and a flared skirt that reaches mid-calf, slightly lifted by a gentle sea breeze. The beach behind her features fine, pale golden sand with subtle footprints, leading to calm turquoise waves under a clear blue sky with soft, wispy clouds. The lighting is natural daylight, casting soft shadows to her left, indicating late afternoon sun. The horizon line is visible in the background, with a faint silhouette of distant dunes. Her skin tone is fair with a natural glow, and her facial features are delicately defined. The composition is centered on her figure, framed from mid-thigh up, with shallow depth of field blurring the distant waves slightly.

Type # to reference inputs.

Image URL*

Hint: Drag and drop image files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: jpg, jpeg, png, webp, gif, avif, heic, heif

Strength

Loras

Additional Settings

Customize your input with more control.

Your request will cost $0.0085 per megapixel.

Result

Idle

What would you like to do next?

Download

{
  "images": [
    {
      "width": 992,
      "content_type": "image/png",
      "url": "https://storage.googleapis.com/falserverless/example_outputs/z-image-turbo-i2i-output.png",
      "height": 1728
    }
  ],
  "prompt": ""
}

Your request will cost $0.0085 per megapixel.

Z-Image Turbo | [image-to-image]

Tongyi-MAI's Z-Image Turbo delivers image-to-image generation with custom LoRA support at $0.0085 per megapixel. This 6B parameter model trades maximum resolution for rapid iteration speed and cost efficiency, making it 10-15x more cost-effective than alternatives with 117 generations per dollar. Built for developers running high-volume image transformation workflows where iteration speed and budget constraints matter more than absolute quality ceilings.

Built for: Product variant generation | Style transfer at scale | Rapid prototyping with custom LoRAs

Performance That Scales

At $0.0085 per megapixel versus $0.039+ for competitors, Z-Image Turbo delivers 117 generations per dollar, making it more cost-effective for high-volume workflows.

Metric	Result	Context
Inference Steps	1-8 steps	Configurable quality/speed tradeoff, default 8 steps
Cost per Megapixel	$0.0085	117 generations per $1.00 on fal
Batch Generation	1-4 images	Per-request parallelization for variant testing
LoRA Capacity	Up to 3 LoRAs	Simultaneous application of custom training weights
Image Size Options	Auto-sizing	Adaptive resolution based on input dimensions

Image-to-Image Generation With Custom Training

Z-Image Turbo processes reference images through Tongyi-MAI's 6B architecture, applying text prompts to transform existing visuals rather than generating from scratch. This contrasts with pure text-to-image models by preserving compositional structure while allowing targeted modifications through natural language.

What this means for you:

Reference-guided generation: Transform existing images with text prompts while maintaining core composition and layout structure
Custom LoRA support: Apply up to 3 trained LoRA weights simultaneously for style control, character consistency, or brand-specific aesthetics
Strength control: Adjust transformation intensity from 0-1.0 to balance between original image preservation and prompt adherence
Flexible output formats: Export as JPEG, PNG, or WebP with configurable quality settings for different distribution channels

Technical Specifications

Spec	Details
Architecture	Z-Image Turbo 6B
Input Formats	Image URL (JPEG, PNG, WebP, GIF, AVIF) + text prompt
Output Formats	JPEG, PNG, WebP with configurable quality
Transformation Control	Strength parameter (0.0-1.0) for conditioning intensity
License	Commercial use permitted

API Documentation | Quickstart Guide | Pricing

How It Stacks Up

FASHN Virtual Try-On V1.5 ($0.029 per image) vs Z-Image Turbo ($0.0085/MP): Z-Image Turbo prioritizes flexible transformation with custom LoRA support for general-purpose workflows at 3-4x lower cost. FASHN specializes in garment-specific try-on with body pose preservation for e-commerce product visualization.

Image Editing endpoints (Age Progression, Wojak Style, Reframe): Z-Image Turbo trades task-specific optimization for general-purpose flexibility through LoRA training. Specialized endpoints deliver preset transformations without requiring custom training, ideal for standardized editing workflows where consistency matters more than creative control.

Z-Image Turbo | [image-to-image]

Built for: Product variant generation | Style transfer at scale | Rapid prototyping with custom LoRAs

Performance That Scales

At $0.0085 per megapixel versus $0.039+ for competitors, Z-Image Turbo delivers 117 generations per dollar, making it more cost-effective for high-volume workflows.

Metric	Result	Context
Inference Steps	1-8 steps	Configurable quality/speed tradeoff, default 8 steps
Cost per Megapixel	$0.0085	117 generations per $1.00 on fal
Batch Generation	1-4 images	Per-request parallelization for variant testing
LoRA Capacity	Up to 3 LoRAs	Simultaneous application of custom training weights
Image Size Options	Auto-sizing	Adaptive resolution based on input dimensions

Image-to-Image Generation With Custom Training

What this means for you:

Reference-guided generation: Transform existing images with text prompts while maintaining core composition and layout structure
Custom LoRA support: Apply up to 3 trained LoRA weights simultaneously for style control, character consistency, or brand-specific aesthetics
Strength control: Adjust transformation intensity from 0-1.0 to balance between original image preservation and prompt adherence
Flexible output formats: Export as JPEG, PNG, or WebP with configurable quality settings for different distribution channels

Technical Specifications

Spec	Details
Architecture	Z-Image Turbo 6B
Input Formats	Image URL (JPEG, PNG, WebP, GIF, AVIF) + text prompt
Output Formats	JPEG, PNG, WebP with configurable quality
Transformation Control	Strength parameter (0.0-1.0) for conditioning intensity
License	Commercial use permitted

API Documentation | Quickstart Guide | Pricing

fal-ai/z-image/turbo/image-to-image/lora, details and endpoints

fal-ai/z-image/turbo/image-to-image/lora

Input

Result

What would you like to do next?

Z-Image Turbo | [image-to-image]

Performance That Scales

Image-to-Image Generation With Custom Training

Technical Specifications

How It Stacks Up

Z-Image Turbo | [image-to-image]

Performance That Scales

Image-to-Image Generation With Custom Training

Technical Specifications

How It Stacks Up